SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared stat
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Agentic Resource Discovery: Let agents search →
- LinkedLinked via arxiv author · 85%Yuyao Zhang →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Junjie Gao →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Zhengxian Wu →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Jiaming Fan →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Jin Zhang →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Shihan Ma →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”
- LinkedLinked via arxiv author · 85%Yao Yao →
“SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration”